About: Center for Large Scale Multi-modal Data Interpretation

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Center for Large Scale Multi-modal Data Interpretation Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Projekt, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	http://linked.opendata.cz/ontology/domain/vavai/Projekt
rdfs:seeAlso	http://www.isvav.cz/projectDetail.do?rowId=GBP103/12/G084
Description	The project aims at exploiting large collections of unlabeled multi-modal data, mainly video footage, to further state-of-the-art in video, audio and natural language understanding, interpretation, annotation and retrieval by combining unsupervised and semi-supervised learning. It will address problems that are very difficult (some probably impossible) to solve in a single modality by adopting an interdisciplinary approach. Progress in individual areas - vision, language and speech will be achieved by co-training and by exploiting results of other modalities as cross-training data. For efficient processing of large data collections, the project will also concern generic problems of organization, indexing, and searching based on similarity that is critical for building real-life applications. The consortium comprises internationally-recognized groups possessing cutting edge expertise in the research areas. The project will benefit from sharing of expertise, data, and methodologies. Besides scientific results presented in publications, two demonstrators will be produced. (en) Projekt má za cíl využít velmi rozsáhlá neanotovaná multimodální data, převážně videozáznamy, k významnému posunu stavu poznání v oblasti porozumění, interpretace, anotace a vyhledávání obrazových sekvencí, řečového signálu a přirozeného jazyka a to kombinací metod založených na učení bez učitele. Zaměří se na problémy, které jsou z pohledu jedné modality velmi těžko řešitelné a využije interdisciplinárního přístupu. Pokrok v jednotlivých oborech (vidění, řeč, jazyk) bude dosažen kombinací metoda a zejména křížovým učením, kdy výstup jedné z modalit bude zdrojem trénovacích dat druhých modalit. Za účelem efektivního zpracování velkých souborů dat všech modalit, se projekt také zaměří na obecné problémy organizace, indexace a vyhledávání na základě podobnosti, což má velký význam při budování skutečných aplikací. Konsorcium se skládá z mezinárodně uznávaných pracovišť, dosahujících špičkové výsledky. V projektu. dojde k přenosu znalostí, metodologií a řešených problémů. Kromě vědeckých výstupů ve formě publikací budou výstupem projektu dva demonstrátory
Title	Center for Large Scale Multi-modal Data Interpretation (en) Centrum pro multi-modální interpretaci dat velkého rozsahu
skos:notation	GBP103/12/G084
http://linked.open...avai/cep/aktivita	Projects for promotion of excellence in basic research
http://linked.open...kovaStatniPodpora	http://linked.opendata.cz/resource/domain/vavai/projekt/GBP103%2F12%2FG084/celkovaStatniPodpora
http://linked.open...ep/celkoveNaklady	http://linked.opendata.cz/resource/domain/vavai/projekt/GBP103%2F12%2FG084/celkoveNaklady
http://linked.open...datumDodatniDoRIV	2015-02-09 (xsd:date)
http://linked.open...i/cep/druhSouteze	VS - Veřejná soutěž ve výzkumu a vývoji
http://linked.open...ep/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open.../cep/fazeProjektu	101113049
http://linked.open...ai/cep/hlavniObor	IN - Informatika
http://linked.open...vai/cep/kategorie	ZV - Základní výzkum
http://linked.open.../cep/klicovaSlova	multimodal data understanding video annotation information extraction information retrieval natu (en)
http://linked.open...ep/partnetrHlavni	Fakulta elektrotechnická
http://linked.open...inujicichPrijemcu	0 (xsd:int)
http://linked.open...cep/pocetPrijemcu	1 (xsd:int)
http://linked.open...ocetSpoluPrijemcu	3 (xsd:int)
http://linked.open.../pocetVysledkuRIV	78 (xsd:int)
http://linked.open...enychVysledkuVRIV	78 (xsd:int)
http://linked.open...lneniVMinulemRoce	2014-04-07 (xsd:date)
http://linked.open.../prideleniPodpory	http://linked.opendata.cz/resource/domain/vavai/cep/prideleniPodpory/P103-12-G084
http://linked.open...iciPoslednihoRoku	2015
http://linked.open...atUdajeProjZameru	2015
http://linked.open.../vavai/cep/soutez	SGA02012GA-GB
http://linked.open...usZobrazovaneFaze	DRRVB
http://linked.open...ai/cep/typPojektu	P - Projekt výzkumu a vývoje financovaný ze státního rozpočtu
http://linked.open...ep/ukonceniReseni	2018-12-31 (xsd:date)
http://linked.open.../cep/vedlejsiObor	AI - Jazykověda JD - Využití počítačů, robotika a její aplikace
http://linked.open...ep/zahajeniReseni	2012-01-01 (xsd:date)
http://linked.open...tniCyklusProjektu	ZBBB
is http://linked.open...vavai/riv/projekt of	DISA at ImageCLEF 2014: The search-based solution for scalable image annotation DISA at ImageCLEF 2014 Revised: Search-based Image Annotation with DeCAF Features Person Tagging in Still Images by Fusing Face and Full-body Detections Performance Study of Independent Anchor Spaces for Similarity Searching The Enhanced Flock of Trackers General framework for mining, processing and storing large amounts of electronic texts for language modeling purposes Machine Translation of Medical Texts in the Khresmoi Project Towards Optimal Choice Selection for Improved Hybrid Machine Translation A Key-Pose Similarity Algorithm for Motion Data Retrieval Active-Speaker Detection and Localization with Microphones and Cameras Embedded into a Robotic Head Content-based annotation and classification framework: a general multi-purpose approach Efficiency and Security in Similarity Cloud Services Efficient algorithm for rational kernel evaluation in large lattice sets Efficient Temporal Consistency for Streaming Video Scene Analysis Long-Term Tracking Through Failure Cases Multimedia Information Seeking through Search and Hyperlinking Multi-level Clustering on Metric Spaces Using a Multi-GPU Platform Rule-Based Extraction of English Verb Collocates from a Dependency-Parsed Corpus Simpler unsupervised POS tagging with bilingual projections A Richly Annotated, Multilingual Parallel Corpus for Hybrid Machine Translation A Real-Time Scene Text to Speech System An Efficient Implementation of Probabilistic Linear Discriminant Analysis Syntactic Identification of Occurrences of Multiword Expressions in Text using a Lexicon with Dependency Structures Kernel-mapped Histograms of Multi-scale LBPs for Tree Bark Recognition Semantically Consistent Human Motion Segmentation Tolerant BLEU: a Submission to the WMT14 Metrics Task Towards Fast Multimedia Feature Extraction: Hadoop or Storm Texture-Based Leaf Identification The ML4HMT Workshop on Optimising the Division of Labour in Hybrid Machine Translation Determining Compositionality of Word Expressions Using Various Word Space Models and Measures Determining Compositionality of Word Expressions Using Word Space Models Determining Compositionality of Word Expressions Using Vord Space Models Face-based People Searching in Videos The Flock of Trackers Increasing the quality and quantity of source language data for unsupervised cross-lingual POS tagging. Image Retrieval for Online Browsing in Large Image Collections Arabic Word Generation and Modelling for Spell Checking Detection of Bubbles As Concentric Circular Arrangements Evaluation of Local Detectors and Descriptors for Fast Feature Matching GPU Accelerated Real Time Rotation, Scale and Translation Invariant Image Registration Method Penalty Functions for Evaluation Measures of Unsegmented Speech Retrieval Real-time scene text localization and recognition Secure Metric-Based Index for Similarity Cloud Retrieving Similar Movements in Motion Capture Data Robust Scale-Adaptive Mean-Shift for Tracking Two-View Matching with View Synthesis Revisited Future Trends in Similarity Searching Factor Analysis and Nuisance Attribute Projection Revisited Identifying Walk Cycles for Human Recognition Increasing Robustness of the Flock of Trackers Managing Uncertainty in Semantic Tagging Maintaining consistency of monolingual verb entries with interannotator agreement Motion-Based Tracking of Multiple Low-Relative-Depth Objects A 3D Approach to Facial Landmarks: Detection, Refinement, and Tracking Optimizing semantic granularity for NLP - report on a lexicographic experiment On Complementarity of State-of-the-art Speaker Recognition Systems Optimized Acoustic Likelihoods Computation for NVIDIA and ATI/AMD Graphics Processors Ultra-fast tracking based on zero-shift points On Behaviour of PLDA Models in the Task of Speaker Recognition On Combining Multiple Segmentations in Scene Text Recognition Online Speaker Adaptation of an Acoustic Model Using Face Recognition On Combining Sequence Alignment and Feature-quantization for Sub-image Searching Rank Aggregation of Candidate Sets for Efficient Similarity Search Robust scale-adaptive mean-shift for tracking Relevance Assessment for Visual Video Re-ranking

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software